缓解基于GenAI的自适应系统中的不确定性交互：愿景、挑战与初步指南
Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines
浏览论文内容
中文总结 AI 辅助
本文针对GenAI组件在软件系统中引入的不确定性交互问题，提出一个初步概念框架和缓解函数，以指导全生命周期的缓解策略，并通过三个用例验证其可行性。
中文摘要 AI 辅助
现代软件密集型系统日益集成GenAI组件，包括LLM和智能体子系统，这些组件在系统各层引入了新颖且复合的不确定性来源。自适应系统社区在理解和管理不确定性方面已取得显著进展。GenAI的内在特征，包括概率输出、幻觉、上下文窗口限制和记忆过时，要求重新审视现有的处理不确定性的框架和缓解策略，尤其是不确定性发生与表现之间的交互。本立场文件提出了一个初步的概念框架，为表征和缓解基于GenAI的软件密集型系统中的不确定性交互建立了初步指南。我们认为，缓解措施必须贯穿整个软件生命周期，涵盖需求分析、设计时决策和运行时自适应，这意味着将其与执行时的监控和分析解耦是不可行的。我们引入了缓解函数的概念，该函数将不确定性交互类别、涉及的不确定性类型、系统设计特征、关键性和缓解架构策略映射到受影响的质量属性及相应的权衡。作为概念验证，我们将该框架应用于三个说明性用例：LLM服务、AI驱动的软件运营和智能体云管理。
英文摘要
Modern software-intensive systems increasingly incorporate GenAI components, including LLM and agentic subsystems, which introduce novel and compounding sources of uncertainty across system layers. The self-adaptive systems community has made significant strides in understanding and managing uncertainty. The intrinsic characteristics of GenAI, including probabilistic outputs, hallucinations, context window limitations, and memory staleness, demand a re-examination of existing frameworks and mitigation strategies for dealing with uncertainty, and especially, the interactions among uncertainty occurrences and manifestations. This position paper posits an initial conceptual framework that establishes preliminary guidelines for characterizing and mitigating uncertainty interactions in GenAI-based software-intensive systems. We argue that mitigation must be considered across the full software lifecycle, encompassing requirements analysis, design-time decisions, and run-time adaptations, which implies the unfeasibility of decoupling it from monitoring and analysis at execution. We introduce the notion of a mitigation function that maps uncertainty interaction categories, involved uncertainty types, system design characteristics, criticality, and mitigating architectural tactics to impacted quality attributes and corresponding tradeoffs. As a proof of concept, we apply the framework to three illustrative use cases: LLM serving, AI-driven software operations, and agentic cloud management.
发表机构
- IIIT Hyderabad（海得拉巴国际信息技术学院）
- Universidad Icesi（伊塞西大学）
- University of Victoria（维多利亚大学）
- Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
- Universidad de Los Andes（安第斯大学）
- Trinity College Dublin（都柏林圣三一学院）
- York University（约克大学）
机构由 AI 辅助整理，请以论文原文为准。
